Device, program, method, and system for providing learned models

A system comprising:

• at least one storage device storing at least a plurality of neural network models, each of the plurality of neural network models is pre-trained;
• and
• at least one processor configured to:
• obtain a first neural network model by searching, based on information regarding at least one of an environment or a condition, from the plurality of neural network models;
• and
• generate a second neural network model by performing, using additional learning data, additional learning on the first neural network model,
• wherein each of the plurality of neural network models is configured to be used for additional learning, and each of the plurality of neural network models is associated with information used for the search.

A server comprising:

• at least one storage device storing a plurality of neural network models, each of the plurality of neural network models is pre-trained;
• and
• at least one processor configured to:
• obtain a first neural network model by searching, based on information regarding at least one of an environment or a condition, from the plurality of neural network models;
• and
• transmit the first neural network model to at least one device, the at least one device being configured to generate a second neural network model by performing, using additional learning data, additional learning on the first neural network model,
• wherein each of the plurality of neural network models is configured to be used for additional learning, and each of the plurality of neural network models is associated with information used for the search.

A device comprising:

• at least one storage device;
• and
• at least one processor configured to:
• receive a first neural network model from at least one server, the at least one server storing a plurality of pre-trained neural network models, the first neural network model being obtained from the plurality of pre-trained neural networks based on information regarding at least one of an environment or a condition;
• and
• generate a second neural network model by performing, using additional learning data, additional learning on the first neural network model,
• wherein each of the plurality of neural network models is configured to be used for additional learning, and each of the plurality of neural network models is associated with information used for the search.